neural-dialogue-metrics/EmbeddingBased

Embedding-based evaluation metrics for dialogue generation.

27
/ 100
Experimental

This tool helps evaluate the quality of responses generated by dialogue systems. It takes a file of human-written 'ground truth' dialogue responses and a file of predicted responses from an AI system. It then provides scores indicating how semantically similar the generated responses are to the ideal ones. Dialogue system developers and researchers would use this to gauge their model's performance.

No commits in the last 6 months.

Use this if you are developing or researching AI dialogue systems and need an automated way to measure the semantic similarity of your system's output against human benchmarks.

Not ideal if you are looking for qualitative feedback on dialogue flow, coherence, or other human-like conversational aspects beyond semantic similarity.

dialogue-system-evaluation natural-language-generation conversational-ai semantic-similarity-scoring
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Python

License

MIT

Last pushed

Jan 08, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/neural-dialogue-metrics/EmbeddingBased"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.